EUVIMEDEUVIMED entdecken
Crossref

Self-Supervised One-Step Diffusion Refinement for Snapshot Compressive Imaging

Shaoguang Huang, Yunzhen Wang, Haijin Zeng, Hongyu Chen, Hongyan Zhang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (7) · 5095-5103

DOI: 10.1609/aaai.v40i7.37423 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Shaoguang Huang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Snapshot compressive imaging (SCI) captures multispectral images (MSIs) using a single coded two-dimensional (2-D) measurement, but reconstructing high-fidelity MSIs from these compressed inputs remains a fundamentally ill-posed challenge. Recent diffusion-based methods improve quality but are limited by scarce MSI training data, domain shifts from RGB-pretrained models, and slow multi-step sampling. These drawbacks restrict their practicality in real-world applications. Unlike prior approaches that rely on expensive iterative refinement or subspace-based diffusion embeddings (e.g., DiffSCI, PSR-SCI)—we introduce a fundamentally different paradigm: a self-supervised One-Step Diffusion (OSD) framework designed specifically for SCI. The key novelty lies in using a single-step diffusion refiner to correct an initial reconstruction, eliminating iterative denoising entirely while preserving generative quality. Moreover, we adopt a self-supervised equivariant learning strategy to train both the predictor and refiner directly from raw 2-D measurements, enabling generalization to unseen domains without ground-truth MSI. To further address limited MSI data, we design a band-selection–driven distillation strategy that transfers core generative priors from large-scale RGB datasets, effectively bridging the domain gap. Extensive experiments confirm that our approach sets a new standard—yielding PSNR gains of 3.44dB, 1.61dB, and 0.28dB on the Harvard, NTIRE, and ICVL datasets respectively, while cutting reconstruction time from 8.9s to just 0.22s per image. These gains in efficiency and adaptability advance SCI reconstruction, enabling accurate and practical real-world deployment.

Zitieren

APA

Huang, S., Wang, Y., Zeng, H., Chen, H., & Zhang, H. (2026). Self-Supervised One-Step Diffusion Refinement for Snapshot Compressive Imaging. Proceedings of the AAAI Conference on Artificial Intelligence, 40(7), 5095-5103. https://doi.org/10.1609/aaai.v40i7.37423

Vancouver

Huang S, Wang Y, Zeng H, Chen H, Zhang H. Self-Supervised One-Step Diffusion Refinement for Snapshot Compressive Imaging. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(7):5095-5103. doi:10.1609/aaai.v40i7.37423

BibTeX
@article{Huang2026,
  author = {Huang, Shaoguang and Wang, Yunzhen and Zeng, Haijin and Chen, Hongyu and Zhang, Hongyan},
  title = {Self-Supervised One-Step Diffusion Refinement for Snapshot Compressive Imaging},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {7},
  pages = {5095--5103},
  doi = {10.1609/aaai.v40i7.37423}
}
Kostenlos starten →